library(tidyverse)
library(ggplot2)
library(lavaan)
library(car)Asian American Quality of Life: Analysis
Data set
This data set is from the 2015 Asian American Quality of Life survey. Participants are from Austin, Texas.
Input data set
qol <- read_csv("AAQoL.csv") |> mutate(across(where(is.character), ~as.factor(.x)))New names:
Rows: 2609 Columns: 231
── Column specification
──────────────────────────────────────────────────────── Delimiter: "," chr
(190): Gender, Ethnicity, Marital Status, No One, Spouse, Children, Gran... dbl
(41): Survey ID, Age, Education Completed, Household Size, Grandparent,...
ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
Specify the column types or set `show_col_types = FALSE` to quiet this message.
• `Other` -> `Other...17`
• `Other` -> `Other...89`qol |> DT::datatable()Warning in instance$preRenderHook(instance): It seems your data is too big for
client-side DataTables. You may consider server-side processing:
https://rstudio.github.io/DT/server.htmlThere are 2,609 responses, some with missing data.
Summary statistics
Gender
qol |> group_by(`Gender`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 3 × 3
Gender n pct
<fct> <int> <dbl>
1 Female 1425 54.6
2 Male 1157 44.3
3 <NA> 27 1.03Age
qol |> filter(!is.na(Age)) |> summarize(age=mean(Age),SD=sd(Age),min=min(Age),max=max(Age))# A tibble: 1 × 4
age SD min max
<dbl> <dbl> <dbl> <dbl>
1 42.9 17.1 18 98Ethnicity
qol |> group_by(Ethnicity) |> summarize(n=n()) |> mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 7 × 3
Ethnicity n pct
<fct> <int> <dbl>
1 Chinese 639 24.5
2 Asian Indian 574 22.0
3 Vietnamese 514 19.7
4 Korean 471 18.1
5 Filipino 265 10.2
6 Other 144 5.52
7 <NA> 2 0.0767Marital Status
qol |> group_by(`Marital Status`) |> summarize(n=n()) |> mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
`Marital Status` n pct
<fct> <int> <dbl>
1 Married 1725 66.1
2 Single 726 27.8
3 Living with a partner 110 4.22
4 Other 30 1.15
5 <NA> 18 0.690Living Alone
qol |> mutate(alone=if_else(`No One`==0,"With Others","Alone")) |>
mutate(alone=factor(alone, levels=c("Alone","With Others"))) |>
group_by(alone) |>
summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 3 × 3
alone n pct
<fct> <int> <dbl>
1 With Others 2392 91.7
2 Alone 212 8.13
3 <NA> 5 0.192Religion
qol |> group_by(Religion) |> summarize(n=n()) |> mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 8 × 3
Religion n pct
<fct> <int> <dbl>
1 Protestant 645 24.7
2 None 506 19.4
3 Catholic 492 18.9
4 Hindu 479 18.4
5 Buddhist 350 13.4
6 Muslim 68 2.61
7 Other 47 1.80
8 <NA> 22 0.843Employment
qol |> mutate(`Full Time Employment`= ifelse(`Full Time Employment`==0,"No","Yes")) |>
group_by(`Full Time Employment`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 3 × 3
`Full Time Employment` n pct
<chr> <int> <dbl>
1 No 1458 55.9
2 Yes 1144 43.8
3 <NA> 7 0.268US Born
qol |>group_by(`US Born`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 3 × 3
`US Born` n pct
<fct> <int> <dbl>
1 No 2353 90.2
2 Yes 239 9.16
3 <NA> 17 0.652Duration
qol |> filter(!is.na(`Duration of Residency`)) |>
summarize(mean=mean(`Duration of Residency`), SD = sd(`Duration of Residency`))# A tibble: 1 × 2
mean SD
<dbl> <dbl>
1 15.6 12.7English Speaking and Difficulty
Primary Speakers
1 = Primary Speaker, 0 = non-primary speaker
qol |> group_by(`Primary Language`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 3 × 3
`Primary Language` n pct
<dbl> <int> <dbl>
1 1 1725 66.1
2 0 859 32.9
3 NA 25 0.958Profiency
qol |> group_by(`English Speaking`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
`English Speaking` n pct
<fct> <int> <dbl>
1 Very well 974 37.3
2 Well 808 31.0
3 Not well 632 24.2
4 Not at all 177 6.78
5 <NA> 18 0.690qol |> group_by(`English Difficulties`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
`English Difficulties` n pct
<fct> <int> <dbl>
1 Not at all 772 29.6
2 Not much 733 28.1
3 Much 549 21.0
4 Very much 516 19.8
5 <NA> 39 1.49Familiarity with America and Ethnic Origin
qol |> group_by(`Familiarity with America`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
`Familiarity with America` n pct
<fct> <int> <dbl>
1 High 1238 47.5
2 Low 721 27.6
3 Very high 498 19.1
4 Very low 123 4.71
5 <NA> 29 1.11qol |> group_by(`Familiarity with Ethnic Origin`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
`Familiarity with Ethnic Origin` n pct
<fct> <int> <dbl>
1 High 1369 52.5
2 Very high 864 33.1
3 Low 295 11.3
4 Very low 51 1.95
5 <NA> 30 1.15Comparing Familiarity with Ethnic Origin and America,
qol |> group_by(`Familiarity with Ethnic Origin`,`Familiarity with America`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))`summarise()` has grouped output by 'Familiarity with Ethnic Origin'. You can
override using the `.groups` argument.# A tibble: 23 × 4
# Groups: Familiarity with Ethnic Origin [5]
`Familiarity with Ethnic Origin` `Familiarity with America` n pct
<fct> <fct> <int> <dbl>
1 High High 711 51.9
2 High Low 431 31.5
3 Very high High 422 48.8
4 Very high Very high 250 28.9
5 Very high Low 167 19.3
6 High Very high 165 12.1
7 Low Low 109 36.9
8 Low High 91 30.8
9 Low Very high 67 22.7
10 High Very low 51 3.73
# ℹ 13 more rowsIdentifying to the ethnic community
qol |> group_by(`Identify Ethnically`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
`Identify Ethnically` n pct
<fct> <int> <dbl>
1 Somewhat close 1211 46.4
2 Very close 1039 39.8
3 Not very close 293 11.2
4 <NA> 35 1.34
5 Not at all 31 1.19Belonging to the ethnic community
qol |> group_by(`Belonging`) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 5 × 3
Belonging n pct
<fct> <int> <dbl>
1 Somewhat 1255 48.1
2 Very much 766 29.4
3 Not very much 450 17.2
4 Not at all 87 3.33
5 <NA> 51 1.95Perceived Discrimination
qol |> group_by(Discrimination) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 3 × 3
Discrimination n pct
<dbl> <int> <dbl>
1 0 1598 61.2
2 1 694 26.6
3 NA 317 12.2Income
qol |> group_by(Income) |> summarize(n=n()) |>
mutate(pct = n/sum(n)*100) |>
arrange(desc(n))# A tibble: 9 × 3
Income n pct
<fct> <int> <dbl>
1 $70,000 and over 993 38.1
2 $0 - $9,999 254 9.74
3 $30,000 - $39,999 207 7.93
4 $10,000 - $19,999 205 7.86
5 <NA> 203 7.78
6 $20,000 - $29,999 198 7.59
7 $60,000 - $69,999 190 7.28
8 $40,000 - $49,999 181 6.94
9 $50,000 - $59,999 178 6.82Analysis
Income
Source of Information association with income after controlling for ethnicity.
qol_1 <- qol |> select(Family,Income,Ethnicity) %>% filter(complete.cases(.)) |>
filter(Family %in%c("Yes","No")) |>
mutate(Family=droplevels(Family))
glm(Family~Income+Ethnicity,data=qol_1,family="binomial") -> mod1
summary(mod1)
Call:
glm(formula = Family ~ Income + Ethnicity, family = "binomial",
data = qol_1)
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.5431 0.1511 3.594 0.000325 ***
Income$10,000 - $19,999 -0.3912 0.1949 -2.007 0.044766 *
Income$20,000 - $29,999 -0.4313 0.1966 -2.194 0.028210 *
Income$30,000 - $39,999 -0.5247 0.1947 -2.694 0.007051 **
Income$40,000 - $49,999 -0.6100 0.2016 -3.026 0.002480 **
Income$50,000 - $59,999 -0.4562 0.2016 -2.263 0.023616 *
Income$60,000 - $69,999 -0.6366 0.1976 -3.222 0.001274 **
Income$70,000 and over -0.5787 0.1470 -3.936 8.3e-05 ***
EthnicityChinese 0.3843 0.1246 3.085 0.002036 **
EthnicityFilipino 0.1972 0.1577 1.250 0.211119
EthnicityKorean -0.2149 0.1316 -1.633 0.102571
EthnicityOther -0.4271 0.2000 -2.135 0.032721 *
EthnicityVietnamese -0.3265 0.1327 -2.461 0.013854 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 3317.8 on 2393 degrees of freedom
Residual deviance: 3252.8 on 2381 degrees of freedom
AIC: 3278.8
Number of Fisher Scoring iterations: 4car::Anova(mod1)Analysis of Deviance Table (Type II tests)
Response: Family
LR Chisq Df Pr(>Chisq)
Income 18.48 7 0.009983 **
Ethnicity 44.93 5 1.499e-08 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Source of Information: Close Friends association with income after controlling for ethnicity.
qol_1 <- qol |> select(`Close Friends`,Income,Ethnicity) %>% filter(complete.cases(.)) |>
group_by(`Close Friends`,Income,Ethnicity) |> summarize(n=n())`summarise()` has grouped output by 'Close Friends', 'Income'. You can override
using the `.groups` argument.corr_table <- xtabs(n~ `Close Friends` +Income + Ethnicity, data=qol_1)
#corr_table
mantelhaen.test(corr_table)
Cochran-Mantel-Haenszel test
data: corr_table
Cochran-Mantel-Haenszel M^2 = 59.769, df = 35, p-value = 0.005648